AWS-BAC: Building Agentic AI with Amazon Bedrock AgentCore

In this course, you will learn to:

• Define agentic AI characteristics and differentiate them from traditional AI systems.
• Identify the core agent components and explain how they interact within an agentic architecture.
• Describe how AgentCore services in Amazon Bedrock support agentic AI capabilities.
• Deploy agents using supported frameworks with AgentCore Runtime.
• Describe the core features and capabilities of AgentCore Runtime.
• Configure serverless execution with session isolation for secure and scalable workloads.
• Configure AgentCore Identity to meet enterprise security requirements.
• Create and apply policies using AgentCore Policy to secure agent tool calls.
• Implement secure token management and permission delegation mechanisms.
• Ensure compliance with data governance standards and audit requirements.
• Implement different tool integration patterns, including built-in tools and protocol-based tools.
• Design and deploy Model Context Protocol (MCP) servers and clients to enable extensible agent capabilities.
• Describe common authentication patterns used for secure agent tool access.
• Configure AgentCore Gateway components to provide secure and authorized access to tools.
• Implement agentic memory patterns tailored to different use cases.
• Configure AgentCore Memory operations to support context-aware agent development.
• Optimize memory performance to support production-scale workloads.
• Configure AgentCore Observability to enable effective production monitoring.
• Implement logging, monitoring, and specialized tracing using Amazon CloudWatch.
• Describe the core features and evaluation capabilities of AgentCore Evaluations.
• Integrate agentic systems with production APIs and enterprise services.
• Design deployment strategies suitable for production environments.
• Assess production readiness and establish continuous improvement processes for agentic systems.

We recommend that attendees of this course have:

• Agentic AI Foundations

This course is intended for:

• Software developers seeking intermediate knowledge for building agentic systems
• Technical professionals exploring AI capabilities and interested in building agentic AI systems
• Development teams building agentic AI solutions.

Module 1: Foundations of Agentic AI Pattern

• Agent building blocks
• Amazon Bedrock AgentCore introduction

Module 2: AgentCore Runtime and Framework Integration

• Supported frameworks and implementation
• AgentCore Runtime overview
• Infrastructure and deployment

Module 3: Security and Identity Management

• Security and identity management
• Securing your agents with AgentCore Identity

Module 4: Tool Integration and AgentCore Gateway

• Amazon Bedrock AgentCore Policy
• Built-in tools and custom integration
• Model Context Protocol (MCP)
• AgentCore Gateway
• Implementing AgentCore Gateway
• Amazon Bedrock AgentCore Policy

Module 5: Agentic Memory Implementation

• Agentic memory core concepts
• AgentCore Memory
• Securing AgentCore Memory

Hands-on Lab: Enhance and Scale Agents with Amazon Bedrock AgentCore

Module 6: Production Monitoring and Observability

• Monitoring agents with AgentCore Observability
• Verifying agent performance with AgentCore Evaluation

Module 7: Course Wrap-up

• Next steps and additional resources
• Course summary